INDEX

Explanations

terms related to animation and animators

oai_token-act-pair · gpt-3.5-turbo

references to animated characters or animation-related terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

holder

-0.77

 Blacks

-0.71

 Mandela

-0.67

peak

-0.67

 blunt

-0.66

 mark

-0.65

stood

-0.64

 poorer

-0.64

 Indies

-0.64

cloth

-0.63

POSITIVE LOGITS

agus

1.24

oji

1.06

agi

1.04

ators

1.02

ator

0.99

osity

0.99

orph

0.97

anche

0.94

ations

0.93

ovie

0.91

Activations Density 0.017%

terms related to animation and animators

references to animated characters or animation-related terms

No Comments

No Known Activations